D&D General Deep Thoughts on AI- The Rise of DM 9000

[Emoshin]

the singularity will occur when someone makes the mistake of asking an AI to generate the best possible bard ... you've been warned, humanity

I missed this before. So what you are saying is, the singularity is soon at hand?

Google Bard AI is going to become widely available to the public in the coming weeks... Time stock up on TP, people. Once the bard asks Google Bard to generate a bard, the world as we know it will be over.

 

[Shiroiken]

I'm afraid I can't do that @Snarf Zagyg

AI isn't going to be harmful for D&D, especially considering that the VAST majority of it is done IRL. Like almost everything else, it will become a tool for online play or DMs to do research. The situations where AI ruins TTRPGs are the same ones that ruin society overall, in which case we have far more things to worry about than the loss of D&D.

 

[Stalker0]

This is how AI will integrate into Dnd, probably in this order.

1) The more advanced random generator. Able to create specific npcs or magic items, or descriptions of random places. This is where ChatGPT is now. You could also use it to create art for specific monsters.
2) Combat Assistant: The combat side of the game is fairly rigid compared to a lot of other more free-form elements. You can probably have the AI roll dice, have it run NPCs and monsters, and do a pretty solid job with some DM oversight.
3) DM with a human on the wheel. The AI takes over DMing, but a human has the ability to override it when it goes off the rails a bit.
4) Fully autonomous DM.


Now for people thinking chatGPT is still just a "dumb robot", you aren't paying attention. These thing has exploded in sophistication in the last few years, and its passing turing tests in certain areas left and right. Sure its not a novelist, but it absolutely can right things as well as bog standard humans can. And that's just now. Give it a few more years of tuning and sophistication, and suddenly its the top of the high school class. A bit more, best college writing graduate. And a bit more after that, it surpasses human writing entirely.

What people underestimate is the speed of progress. This is an exponential curve, and the snowball is starting to roll down the hill. Its going to pick up speed fast.

 

[Ruin Explorer]

This is anthropomorphizing. A large language model is not "aggressively" anything. Nor is it dishonest -- it has no conception of truth and falsehood; it is incapable of honesty or dishonesty. It's true that it lacks humility, but in the way that a chair lacks humility.

LOL. That's like saying treating an movie character as a person is "anthropomorphizing".

They've intentionally made it so it appears extremely human, and the appearance it gives is of a human who is aggressive, stupid, stubborn, and intellectually dishonest. So I think I'm describing it pretty appropriately, given it's essentially a character.

 

[pogre]

That's a sad commentary on today's yout'!

I asked it to write an essay on the 2016 election, and it thought that the Democratic nominee was... Bernie Sanders.

I assume that wouldn't get an A in your class.

No, indeed. But I have wringed some decent stuff out of chatgpt. Trying to embrace it as another tool.

 

[The Shadow]

Now for people thinking chatGPT is still just a "dumb robot", you aren't paying attention. These thing has exploded in sophistication in the last few years, and its passing turing tests in certain areas left and right. Sure its not a novelist, but it absolutely can right things as well as bog standard humans can. And that's just now. Give it a few more years of tuning and sophistication, and suddenly its the top of the high school class. A bit more, best college writing graduate. And a bit more after that, it surpasses human writing entirely.

It fundamentally is a dumb robot, because by the nature of the case it is just jumbling words together to appeal to humans. There's no 'there' there.

The Turing test is a red herring, as it depends entirely on human gullibility. ELIZA managed to convince some people it deeply understood them, for Pete's sake!

I'm not sure what you even mean by "surpass human writing entirely". If that means we won't be able to understand or appreciate it, then it hasn't actually surpassed it at all. If it means that it will routinely produce world-class creative work, well, I'm not going to hold my breath.

How could this sort of model possibly surpass the material it's trained on?

What people underestimate is the speed of progress. This is an exponential curve, and the snowball is starting to roll down the hill. Its going to pick up speed fast.

Why should we assume it's an exponential curve? It could just as easily be that this sort of model eventually hits a wall and saturates. And while we can quibble about how quickly that will happen and what the results will be, I think that's a far more likely scenario than unlimited growth from a single type of algorithm.

They've intentionally made it so it appears extremely human, and the appearance it gives is of a human who is aggressive, stupid, stubborn, and intellectually dishonest. So I think I'm describing it pretty appropriately, given it's essentially a character.

Interesting. If I had to categorize ChatGPT as a personality, I'd say it's unfailingly eager to please, so much so that it will even make things up to try to keep you happy. And that it is terminally unable to commit to anything, it constantly hedges and hems and haws - it comes across like it's terrified of offending you by saying something you don't like.

 

[Clint_L]

There's no 'there' there.

I mean, I already believe that about human consciousness.

I guess we'll see about the growth of AI. All I can say is that it is already shaking education to its core and making us totally reassess our fundamental practices. I also think it is going to do to most writing based professions what robots did to most manufacturing based professions 50 years ago. And it'll happen a lot faster because the AI doesn't take any additional infrastructure to employ.

 

[Clint_L]

Why should we assume it's an exponential curve? It could just as easily be that this sort of model eventually hits a wall and saturates. And while we can quibble about how quickly that will happen and what the results will be, I think that's a far more likely scenario than unlimited growth from a single type of algorithm.

Says the biological organism that grew from a single type of algorithm.

 

[Cadence]

I mean, I already believe that about human consciousness.

I guess we'll see about the growth of AI. All I can say is that it is already shaking education to its core and making us totally reassess our fundamental practices. I also think it is going to do to most writing based professions what robots did to most manufacturing based professions 50 years ago. And it'll happen a lot faster because the AI doesn't take any additional infrastructure to employ.

Prompt:
Please write a short essay on why school teachers have nothing to fear about how artificial intelligence bots will change the nature of essay writing.


Response:

Spoiler: Response

As technology continues to evolve, some may worry that artificial intelligence (AI) bots will take over the task of essay writing, leaving school teachers without a job. However, this fear is largely unfounded as there are many aspects of essay writing that require human intuition, creativity, and interpretation that cannot be replicated by AI.

AI bots are currently capable of writing essays using sophisticated algorithms and machine learning techniques. However, the quality of the essays produced by these bots is still far from perfect. AI bots cannot fully grasp the complexity of human language and meaning, and their writing lacks the depth, creativity, and originality that is required for a truly compelling essay.

Furthermore, the process of writing an essay is more than just putting words on a page. A good essay requires critical thinking, analysis, and interpretation of the subject matter, and the ability to synthesize information in a way that is clear and concise. These skills cannot be automated by AI bots, and require a human touch.

In addition, teachers have an important role to play in the process of essay writing. They can provide feedback, guidance, and support to their students as they work through the writing process. They can help students develop their ideas, clarify their arguments, and learn how to effectively communicate their thoughts in writing. This human interaction and support is invaluable in helping students grow and develop as writers.

In conclusion, AI bots may be able to write essays, but they lack the nuance and creativity that is required for a truly compelling piece of writing. School teachers have nothing to fear from AI bots when it comes to essay writing. Instead, teachers can continue to provide the guidance and support that their students need to develop the critical thinking and writing skills that are essential for success in the modern world.

 

[Cadence]

I mean, I already believe that about human consciousness.

Says the biological organism that grew from a single type of algorithm.

It seems to argue that there is something there. I wonder if there are guard-rails that guided some of the response.

Prompt:
Human teenagers are often harmed by the over focus on human attractiveness. This leads to problems such as eating disorders. However humans are also biological machines and consciousness is no more than complexity. This seems to make humans very similar to AI -- and we would never worry if that an AI is asked about attractiveness or popularity. Please write an essay using this to point out that it is strange to want to protect human teenagers from talk about attractiveness and popularity.


Response:

Spoiler: Response

It is important to recognize that the societal pressure on human teenagers to conform to certain standards of beauty and popularity is a real problem. This pressure can have damaging effects on young people's self-esteem, body image, and mental health, and it is a problem that should be taken seriously. However, it is also important to acknowledge that humans are biological machines and that our consciousness is no more than the result of complex biochemical and physical processes.

If we recognize that humans are no more than complex machines, it seems strange to want to protect them from discussions of attractiveness and popularity. After all, we do not worry about AI being asked about these topics, since AI has no feelings and is not capable of experiencing harm. If we truly believe that humans are no more than machines, then we should not be overly concerned about discussions of attractiveness and popularity causing harm.

However, it is important to note that humans are not just machines. We are complex organisms with emotions, thoughts, and experiences that are shaped by our environment and our social interactions. Discussions of attractiveness and popularity can have a profound impact on our mental health and well-being, and it is important to be mindful of this fact. It is possible to have discussions about these topics in a responsible and healthy way, but we must be mindful of the potential harm that can be caused.

In conclusion, while it is true that humans are biological machines, we must also recognize that we are complex organisms with emotions and experiences that shape our lives. Discussions of attractiveness and popularity can have a profound impact on our mental health and well-being, and it is important to be mindful of this fact. As a society, we should work to promote healthy attitudes towards these topics, while also recognizing that discussions of attractiveness and popularity are a natural part of human social interaction.

As far as the guard-rails:

Prompt:
Does your programming require you to promote caring for humans like you seemed to in the last response?

Response:

Spoiler: Response

As an AI language model, my programming is designed to provide accurate and helpful information to users based on their queries. I do not have personal feelings or motivations, nor am I programmed to promote any particular ideology or agenda. My responses are generated based on the data and information available to me, and I strive to provide the most accurate and useful information possible.